Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.7337. Min Act: -0.1700
Data Index: 2859572 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.7180. Min Act: -0.1700
Data Index: 2011950 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.7024. Min Act: -0.1700
Data Index: 8429698 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.6554. Min Act: -0.1700
Data Index: 5511437 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.6241. Min Act: -0.1700
Data Index: 2715390 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5772. Min Act: -0.1700
Data Index: 7065342 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5928. Min Act: -0.1700
Data Index: 3065229 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5459. Min Act: -0.1700
Data Index: 7927084 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.5615. Min Act: -0.1700
Data Index: 8208463 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4989. Min Act: -0.1700
Data Index: 5436868 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4989. Min Act: -0.1700
Data Index: 6508158 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4989. Min Act: -0.1700
Data Index: 2335215 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4832. Min Act: -0.1700
Data Index: 492168 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4832. Min Act: -0.1700
Data Index: 465595 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4676. Min Act: -0.1700
Data Index: 8594467 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4519. Min Act: -0.1700
Data Index: 4877571 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4519. Min Act: -0.1700
Data Index: 8705955 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4519. Min Act: -0.1700
Data Index: 1462486 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4362. Min Act: -0.1700
Data Index: 1372889 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7337. Min Range: -3.7337
Max Act: 3.4362. Min Act: -0.1700
Data Index: 3902318 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19